Multi-agent Scaling Across Disjunctive and Compensatory Tasks
Larger LLM teams rarely help: plurality voting wastes a 5–20 point coverage gain, and shared bias dominates Fermi error.
1 stories, newest first · one card per story
Larger LLM teams rarely help: plurality voting wastes a 5–20 point coverage gain, and shared bias dominates Fermi error.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views